Attention select de mass (dépendance de mixOmics) prend le pas sur dplyr
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.1.1 ✓ dplyr 1.0.5
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## Loading required package: MASS
##
## Attaching package: 'MASS'
## The following object is masked from 'package:dplyr':
##
## select
## Loading required package: lattice
##
## Loaded mixOmics 6.14.1
## Thank you for using mixOmics!
## Tutorials: http://mixomics.org
## Bookdown vignette: https://mixomicsteam.github.io/Bookdown
## Questions, issues: Follow the prompts at http://mixomics.org/contact-us
## Cite us: citation('mixOmics')
##
## Attaching package: 'mixOmics'
## The following object is masked from 'package:purrr':
##
## map
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
chemin <- "Raw_brut/"
#Echantillons
Sample <- read.csv2(paste0(chemin,"MI_Covariates.csv"))
Corres_var <- read.csv2(paste0(chemin,"MI_Covariates_corresp.csv"))
Corres_ID <- read.csv2(paste0(chemin,"Mb_Info_seq.csv"))
#Métabolites
NMR_CPMG <- read.csv2(paste0(chemin,"NMR_CPMG.csv"))
NMR_NOESY <- read.csv2(paste0(chemin,"NMR_NOESY1D.csv"))
List_cplte_CPMG <- read.csv2(paste0(chemin,"NMR_BUCKET_CPMG_LIST_assigned.csv"))
List_cplte_NOESY <- read.csv2(paste0(chemin,"NMR_BUCKET_NOESY_LIST_assigned.csv"))
List_CPMG <- read.csv2(paste0(chemin,"List_NMR.csv"))
List_NOESY <- read.csv2(paste0(chemin,"List_NOESY.csv"))
## Homogénéisation des noms de variables
##Attention package mass possède un select qui annule celui de dplyr
Sample_ID <- left_join(Sample,Corres_ID,by=c("DonorID"="DonorId")) %>%
relocate("Echantillon", .before = "DonorID") %>%
dplyr::select(-"SeqDepth",-"DonorID")
rownames(Sample_ID) = Sample_ID$Echantillon
#Met la variable AGE en catégorie non hierarchisé et transformation en factor
Sample_ID <- Sample_ID %>%
dplyr::select(-"Echantillon") %>%
mutate(age = factor(AGE, levels = c(1, 2, 3, 4, 5), labels = c("[20-29]", "[30-39]", "[40-49]", "[50-59]", "[60-69]"))) %>%
mutate(SEX = factor(SEX))
Sample_ID$tabac <- factor(Sample_ID$tabac)
CPMG <- left_join(NMR_CPMG,Corres_ID,by=c("DonnorID"="DonorId")) %>%
relocate("Echantillon", .before = "DonnorID") %>%
dplyr::select(-c("DonnorID","Sample_type","VagueManip","Date","Spectre2","Exp"))
rownames(CPMG) = CPMG$Echantillon
CPMG <- CPMG %>%
dplyr::select(-Echantillon)
NOESY <- left_join(NMR_NOESY,Corres_ID,by=c("DonnorID"="DonorId")) %>%
relocate("Echantillon", .before = "DonnorID") %>%
dplyr::select(-c("DonnorID","Spectre2","Exp","Sample_type","VagueManip","CV_Grps","CV_Grps6","CV_Grps7","CV_Grps8","CV_Grps9"))
rownames(NOESY) = NOESY$Echantillon
NOESY <- NOESY %>%
dplyr::select(-Echantillon)
# Passage en matrice
Noesy <- as.matrix(NOESY)
Cpmg <- as.matrix(CPMG)
# ?mixOmics
# #selection des métabolites d'interêts. Voir pour transposer et ne selectionner que certaines col avec métabo nommés
# List_CPMG1 <- t(List_CPMG)
# colnames(List_CPMG1) = List_CPMG1[1,]
# List_CPMG2 <- t(List_CPMG1[3,])
# List_CPMG2 <- t(List_CPMG2)ncomp correspond: The number of components to include in the model for each block (does not necessarily need to take the same value for each block). Je ne sais pas. J’ai mis 3 pour le tabac Ne fonctionne pas pour CPMG
## a Partial Least Squares - Discriminant Analysis is being performed (PLS-DA)
## a Partial Least Squares - Discriminant Analysis is being performed (PLS-DA)
#les 2 ensembles ne fonctionnent pas
#Data_mix <- mixOmics(X=c(Noesy,Cpmg), Y=Sample_ID$tabac, ncomp=3)
#Message :
#Error in if (length(Y) != nrow(X)) stop("unequal number of rows in 'X' and 'Y'.") :
# l'argument est de longueur nulle
#head(Sample_ID$tabac)
#help(package='mixOmics')Graph issus du Package mixOmics
#CPMG_filt <- CPMG[-match(c("L31R124"), table = rownames(CPMG)), ]
#PCA(CPMG, scale.unit = TRUE, ncp = 5, graph = TRUE)## **Results for the Principal Component Analysis (PCA)**
## The analysis was performed on 846 individuals, described by 215 variables
## *The results are available in the following objects:
##
## name description
## 1 "$eig" "eigenvalues"
## 2 "$var" "results for the variables"
## 3 "$var$coord" "coord. for the variables"
## 4 "$var$cor" "correlations variables - dimensions"
## 5 "$var$cos2" "cos2 for the variables"
## 6 "$var$contrib" "contributions of the variables"
## 7 "$ind" "results for the individuals"
## 8 "$ind$coord" "coord. for the individuals"
## 9 "$ind$cos2" "cos2 for the individuals"
## 10 "$ind$contrib" "contributions of the individuals"
## 11 "$call" "summary statistics"
## 12 "$call$centre" "mean of the variables"
## 13 "$call$ecart.type" "standard error of the variables"
## 14 "$call$row.w" "weights for the individuals"
## 15 "$call$col.w" "weights for the variables"
#fviz_pca_ind(res.pca, geom.ind = "point", habillage = Sample_ID$SEX, addEllipses = TRUE)
#fviz_pca_ind(res.pca, geom.ind = "point", habillage = Sample_ID$age, addEllipses = TRUE)
fviz_pca_ind(res.pca, geom.ind = "point", habillage = Sample_ID$tabac, addEllipses = TRUE)